{"id":"W4388223267","doi":"10.1111/emip.12582","title":"Comparing Large‐Scale Assessments in Two Proctoring Modalities with Interactive Log Data Analysis","year":2023,"lang":"en","type":"article","venue":"Educational Measurement Issues and Practice","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Medical Council of Canada","funders":"","keywords":"Modalities; Comparability; Modality (human–computer interaction); Test (biology); Scale (ratio); Medicine; Computer science; Human–computer interaction; Mathematics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002164447,0.0001080422,0.0002141866,0.0002895569,0.0001352275,0.00007875306,0.00009814365,0.00002445611,0.00009303857],"category_scores_gemma":[0.001169057,0.00009533534,0.00001790496,0.0008304546,0.00002784771,0.0007596993,0.0000596219,0.0001983901,0.00003520074],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002056722,"about_ca_system_score_gemma":0.0004120805,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004610889,"about_ca_topic_score_gemma":0.003140795,"domain_scores_codex":[0.9983882,0.0001600628,0.0002957809,0.0003620409,0.000571355,0.0002225542],"domain_scores_gemma":[0.9983239,0.0006007801,0.0001343032,0.0003297607,0.0005141077,0.00009711559],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0005639302,0.0007361787,0.9779504,0.0001460324,0.0005277825,0.000005141645,0.01497887,0.0003468847,0.0001177934,0.000718736,0.001168079,0.002740156],"study_design_scores_gemma":[0.0003635056,0.0002487792,0.8119233,0.0005604404,0.00123737,0.00003960701,0.1338442,0.01807157,0.0005523928,0.001390188,0.03142526,0.0003434051],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9452178,0.001071018,0.0009661897,0.04610939,0.0005437516,0.0006083435,0.00001393392,0.00005278895,0.005416753],"genre_scores_gemma":[0.9947213,0.0002365149,0.003443235,0.0002737172,0.0003816273,0.00006959916,0.0003108289,0.00001045418,0.0005527437],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1660272,"threshold_uncertainty_score":0.6970315,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5444063599822654,"score_gpt":0.5751607052320205,"score_spread":0.03075434524975507,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}